← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-04-05
Performance
8k
tokens
367.7
PP tok/s
17.8
TG tok/s
22281
TTFT (ms)
15.0
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.4
macOS macOS 15.2
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 341.5 46.1 14.2 GB view
4k 361.6 29.0 14.8 GB view
8k 367.7 17.8 15.0 GB current
16k 358.7 10.0 15.4 GB view
Batching Results
Batch Size TG tok/s Speedup
46.1 1.00×
59.4 1.29×
70.5 1.53×
78.5 1.70×